Abstract: A georeferenced trajectory system for vehicles receives trajectory data generated by a plurality of vehicle sensors and scaffolds of previously generated maps and aligns geometry data for a geographic region and trajectory data from the received data from different map builds. A scaffold of a geographic region to be mapped during an initial map build is generated, and the trajectory data from respective map builds is aligned with the scaffold of previously generated maps to generate a map of the geographic region. The resulting map expands the coverage of the existing map such that old and new map data is in a common consistent reference frame whereby the map may be built incrementally by merging or expanding local scaffolds and filling in the merged or expanded scaffold while ensuring global consistency.

Abstract: A laser range finder projects light while changing a direction in a horizontal direction at a predetermined angle with respect to a vertical direction to also receive reflected light of the light, and detects a direction and a distance in which the light is reflected from an obstacle or the like, according to a difference time between a time of light projection and a time of light reception. A normal direction of a flat plane forming a road surface is detected on the basis of a polarized image. The laser range finder projects light such that the light has a predetermined angle with respect to the vertical direction so as to be orthogonal to the normal direction of the flat plane forming the road surface. The laser range finder can be applied to in-vehicle systems.

Abstract: An autonomous driving control device includes a map information input unit, a new map information storage unit, and a calculation unit. The map information input unit includes several input means and several processing means. The calculation unit performs the autonomous driving using the new map information obtained by accessing the new map information storage unit.

Abstract: Described herein are embodiments of a neural network-based task planner (TaskNet) for autonomous vehicle. Given a high-level task, the TaskNet planner decomposes it into a sequence of sub-tasks, each of which is further decomposed into task primitives with specifications. TaskNet comprises a first model for predicating the global sequence of working area to cover large terrain, and a second model for determining local operation order and specifications for each operation. The neural models may include convolutional layers for extracting features from grid map-based environment representation, and fully connected layers to combine extracted features with past sequences and predict the next sub-task or task primitive. Embodiments of the TaskNet are trained using an excavation trace generator and evaluate its performance using a 3D physically-based terrain and excavator simulator.

Abstract: A vehicle control device includes: a driving controller configured to perform first driving control such that one or both of an acceleration or deceleration speed and steering of a vehicle is controlled to travel the vehicle; an occupant intention detector configured to detect an intention of the occupant to switch from manual driving to a state in which the driving controller performs the first driving control; and a one-way traffic determiner configured to determine whether a road on which the vehicle is predicted to be traveling or travel in future is a one-way traffic road. The driving controller determines whether to start the first driving control based on whether the one-way traffic determiner determines the road on which the vehicle is predicted to be traveling or travel in future is the one-way traffic road.

Abstract: A computer-implemented method for intersection communication includes detecting a first vehicle behind a host vehicle and in a same lane as the host vehicle and determining a rear distance between a rear end of the host vehicle and a front end of the first vehicle. The method also includes transmitting a backup request to the first vehicle based on the rear distance and a wait time period between the stop state and a go state controlled by a traffic signal device. Further, the method includes controlling the host vehicle to perform a backup maneuver with respect to an intersection based on the rear distance and the wait time period.

Abstract: In the present invention, when a road surface condition is determined based on information acquired by a camera installed in a vehicle, a route of a host vehicle is predicted and the is determined. A road surface condition determination method and device determines a road surface condition of a predicted route based on information acquired by a camera installed in a host vehicle. A controller predicts a route of the host vehicle by determining a road surface friction coefficient of the predicted route based on information acquired by the camera. The determining of the road surface friction coefficient of the predicted route includes: dividing an ahead-of-vehicle image acquired by the camera in a left-right direction and determining a road surface condition for each of the determination areas, and determining the road surface friction coefficient in the determination areas through which the predicted route will pass.

Abstract: A vehicle control apparatus that controls a vehicle based on a plurality of control states, includes a detection unit configured to detect information of the vehicle and peripheral information of the vehicle and a vehicle control unit configured to control the vehicle based on a detection result of the detection unit. In a case in which the vehicle control unit can execute, based on the detection result of the detection unit, a first control state and a second control state, the vehicle control unit controls the vehicle by selecting a control state prioritizing one of the first control state and the second control state in an overlapping operation condition range.

Abstract: A system, method, and non-transitory computer-readable storage medium to perform a search and rescue mission according to a Layered Search and Rescue (LSAR) methodology using a plurality of Unmanned Aerial Vehicles (UAVs) communicatively connected to a remote server. The LSAR methodology can involve receiving data corresponding to a center of an area corresponding to an adverse/disaster event potentially having survivors at unknown locations; dividing the area into a set of numbered box-shaped layers within the area; calculating a thickness of the box-shaped layers based on a total number of the Unmanned Aerial Vehicles; exclusively assigning one or more of the Unmanned Aerial Vehicles to each box-shaped layer; and controlling the Unmanned Aerial Vehicles to perform the search and rescue mission by selectively switching one or more of the Unmanned Aerial Vehicles between a searcher mode and a rescuer mode.

Abstract: A drawing apparatus is connected to a compound design apparatus. The design apparatus includes at least a display for displaying a drawing, a data base device for storing therein reference data to analyze the drawing, a storage for storing therein analysis data of the drawing, and a computing unit connected to the drawing apparatus to analyze the drawing. The computing unit may include a drawing evaluating section for extracting a graphic image of a particular mechanism part from the drawing generated by the drawing apparatus and for evaluating the graphic image, an analysis model generator for generating, according to a profile of the graphic image, an analysis model having a mechanism equivalent to the graphic image, an analyzer for reading mechanical characteristic data from the data base device, supplying the data to the analysis model, and analyzing the mechanism, and an analysis evaluating section for evaluating analysis results attained from the analyzer.

Abstract: An MPEG video decompression method and apparatus utilizing a plurality of stages interconnected by a two-wire interface arranged as a pipeline processing machine. Control tokens and DATA Tokens pass over the single two-wire interface for carrying both control and data in token format. A token decode circuit is positioned in certain of the stages for recognizing certain of the tokens as control tokens pertinent to that stage and for passing unrecognized control tokens along the pipeline. Reconfiguration processing circuits are positioned in selected stages and are responsive to a recognized control token for reconfiguring such stage to handle an identified DATA Token. A wide variety of unique supporting subsystem circuitry and processing techniques are disclosed for implementing the system, including memory addressing, transforming data using a common processing block, time synchronization, asynchronous swing buffering, storing of video information, a parallel Huffman decoder, and the like.

Abstract: In a work flow system in which work defined beforehand with respect to data processing is executed by a plurality of workers in a plurality of nodes connected to each other through an information network, data processed in a branch source node is divided into split data so that the split data are distributed to some branch destination nodes. The split data processed in the respective branch destination nodes are connected as input data to be given to a connecting destination node. A work flow control engine sets data start and end positions of each of the split data, split data information, and connection data information into a dividing/connecting information table. The work flow control engine renews the data start and end positions in the dividing/connecting information table in accordance with increase/decrease of the split data processed in each of the branch destination nodes.

Abstract: A method and system for managing time synchronization services. The system uses standard management protocols to interface with a time synchronization management information base, which in turn interfaces with a time synchronization services module. A uniform and standard mechanism for managing time synchronization services is provided, which includes a user interface which eliminates the need to learn console commands and eases the administration of time synchronization services.

Abstract: A structure and a format for providing a video signal encoder under the MPEG standard are provided. In one embodiment, the video signal interface is provided with a decimator for providing input filtering for the incoming signals. In one embodiment, the central processing unit (CPU) and multiple coprocessors implements DCT and IDCT and other signal processing functions, generating variable length codes, and provides motion estimation and memory management. The instruction set of the central processing unit provides numerous features in support for such features as alpha filtering, eliminating redundancies in video signals derived from motion pictures and scene analysis. In one embodiment, a matcher evaluates 16 absolute differences to evaluate a "patch" of eight motion vectors at a time.

Abstract: A computer system having a shared system memory, and system software in the computer system, are described herein. One or more user applications execute in the computer system. The computer system has a general purpose, shared system memory that is used for all processing, including video input/output operations and image conversion operations. The computer system also has a multimedia access and control module (MACM), which is the input/output interface between the computer system and the external world. In operation, the MACM receives, at one of its video input ports, video data comprising a video image (such as a frame or a field). The MACM stores the video image in a first buffer contained in a first buffer pool of the system memory. The first buffer pool was previously created by a user application. The user application previously associated the first buffer pool with the MACM's video input port. A video imaging and compression module (VICM) performs image conversion operations.

Abstract: A method, apparatus, and article of manufacture for initial network address configuration using physical address resolution protocol. A device attempts a connection to the network, which causes address resolution (ARP) packets to be generated. The device monitors communications on the network for a specified number of unanswered ARP packets. Thereafter, the device adopt the network address in the unanswered ARP packets and responds to the unanswered ARP packets with the its' physical address.

Abstract: An image processing apparatus which performs motion compensation prediction image decompression by a small circuit scale. The apparatus comprises: an image memory which is equivalent to a processing region and executes the motion compensation; and an adder. The adder executes interpolation calculation in the event that a reference image is constructed from a motion vector of 1/2 accuracy, and its result therefrom is stored in said image memory. Addition process of the reference image and difference data is processed by the same adder in a time sharing manner.

Abstract: This invention presents a multi-beam baseband processor for making post-beamformation adjustments to the complex (in-phase/quadrature) pre-detection scan line samples acquired from a receive beamformer of an ultrasound imaging system. Specifically, the invention includes a programmable finite impulse response (FIR) filter and a programmable complex multiplier. The programmable filter performs signal shaping and sample-rate conversion. The signal shaping capability may be used to compensate for transducer and analog signal path responses, to increase signal-to-noise ratio (SNR) by rejecting out-of-band noise frequencies, to operate as a matched filter to the transmitted waveform shape, and to act as both a smoothing and anti-aliasing filter during rate-conversion operation.

Abstract: A communication utility for establishing real-time, point-to-point communications between processes over a computer network includes apparatus for querying a server as to the network protocol address of another client process, and apparatus for directly establishing a communication link with the client process upon receipt of the network protocol address from the server. In one embodiment, the utility includes a sophisticated user interface having features similar to typical telephony hardware but implementing greater flexibility with software.

Abstract: A method for delivering a message unit to a destination network resource within a transport communications layer includes the steps of configuring a mapping to the destination network resource based upon a source address of the message unit, and sending the message unit to the destination network resource based upon the mapping.